Marine ecological information prediction by using adjacent location spatiotemporal deep learning model with ensemble learning techniques DOI Creative Commons
Yue‐Shan Chang, Shuting Huang, Haobijam Basanta

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102964 - 102964

Published: Dec. 1, 2024

Language: Английский

Weight-based ensemble method for crop pest identification DOI Creative Commons
Miao Chen, Jianji Wang, Yanan Chen

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102693 - 102693

Published: June 21, 2024

Crop pests cause significant losses to agricultural production. Pests can be detected and controlled over time using accurate effective methods, thereby reducing potential losses. However, there are challenges in realistic scenarios, such as diverse pest species complicated environments, which render manual recognition conventional machine learning methods insufficient. To address this issue, deep that automatically extract features have recently been widely used for identification. accurately recognizing images resemble complex real-world scenarios remains a challenging task single model. The ensemble method, combines multiple basic models, provides solution improving performance. In study, we proposed two weight-based VecEnsemble MatEnsemble, constructed from vector- matrix-based weights, respectively. weights combine models significantly influence the performance of methods. Therefore, effectively formulated weight design problem quadratic convex optimization whose has closed-form expression computed efficiently. Our method achieved highest accuracy 77.39% on large-scale complex-scene IP102 dataset, was competitive with those other state-of-the-art Furthermore, conducted comprehensive ablation experiments compare our voting-based approaches illustrate they applicable. These results highlight practical significance production provide foundation further research crop source code is available at https://github.com/shiguangqianmo/WBEnsemble.

Language: Английский

Citations

3
CustomBottleneck-VGGNet: Advanced tomato leaf disease identification for sustainable agriculture DOI
Mohamed Zarboubi, Abdelaaziz Bellout, Samira Chabaa

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 110066 - 110066

Published: Feb. 11, 2025

Language: Английский

Citations

0
Ensemble transfer learning meets explainable AI: A deep learning approach for leaf disease detection DOI Creative Commons
Harit K. Raval, Jyotismita Chaki

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102925 - 102925

Published: Nov. 1, 2024

Language: Английский

Citations

2
Enhancing model robustness to imbalanced species abundance distributions: Eliminating misclassified records via a model-agnostic approach, exemplified by tuna fisheries datasets DOI Creative Commons
Zhexuan Li, Tianjiao Zhang, Liming Song

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102905 - 102905

Published: Nov. 1, 2024

Language: Английский

Citations

1
Diagnosis of Custard Apple Disease Based on Adaptive Information Entropy Data Augmentation and Multiscale Region Aggregation Interactive Visual Transformers DOI Creative Commons
Kunpeng Cui,

Jianbo Huang,

Guowei Dai

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(11), P. 2605 - 2605

Published: Nov. 4, 2024

Accurate diagnosis of plant diseases is crucial for crop health. This study introduces the EDA–ViT model, a Vision Transformer (ViT)-based approach that integrates adaptive entropy-based data augmentation diagnosing custard apple (Annona squamosa) diseases. Traditional models like convolutional neural network and ViT face challenges with local feature extraction large dataset requirements. overcomes these by using multi-scale weighted aggregation interaction module, enhancing both global extraction. The method refines training process, boosting accuracy robustness. With 8226 images, achieved classification 96.58%, an F1 score 96.10%, Matthews Correlation Coefficient (MCC) 92.24%, outperforming other models. inclusion Deformable Multi-head Self-Attention (DMSA) mechanism further enhanced capture. Ablation studies revealed contributed to 0.56% improvement 0.34% increase in MCC. In summary, presents innovative solution disease diagnosis, potential applications broader agricultural detection, ultimately aiding precision agriculture health management.

Language: Английский

Citations

0
An efficient plant disease prediction model based on machine learning and deep learning classifiers DOI
Nirmala Shinde, Asha Ambhaikar

Evolutionary Intelligence, Journal Year: 2024, Volume and Issue: 18(1)

Published: Nov. 26, 2024

Language: Английский

Citations

0
Marine ecological information prediction by using adjacent location spatiotemporal deep learning model with ensemble learning techniques DOI Creative Commons
Yue‐Shan Chang, Shuting Huang, Haobijam Basanta

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102964 - 102964

Published: Dec. 1, 2024

Language: Английский

Citations

0